Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3540 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.6136. Min Act: -0.0000

Data Index: 1935619 (The Pile)

Max Activating Token Index: 899

Text #1

Max Range: 1.6136. Min Range: -1.6136

Max Act: 0.9977. Min Act: -0.0000

Data Index: 914804 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1983. Min Act: -0.0000

Data Index: 601392 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0866. Min Act: -0.0000

Data Index: 1711580 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1177. Min Act: -0.0000

Data Index: 67833 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0976. Min Act: -0.0000

Data Index: 1997219 (The Pile)

Max Activating Token Index: 836

Text #6

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1809319 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1926686 (The Pile)

Max Activating Token Index: 294

Text #8

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0688. Min Act: -0.0000

Data Index: 539484 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1133396 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 1.6136. Min Range: -1.6136

Max Act: 0.9708. Min Act: 0.0000

Data Index: 779886 (The Pile)

Max Activating Token Index: 175

Text #11

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0670. Min Act: -0.0000

Data Index: 1364500 (The Pile)

Max Activating Token Index: 827

Text #12

Max Range: 1.6136. Min Range: -1.6136

Max Act: 0.9200. Min Act: -0.0000

Data Index: 1576436 (The Pile)

Max Activating Token Index: 231

Text #13

Max Range: 1.6136. Min Range: -1.6136

Max Act: 0.9255. Min Act: -0.0000

Data Index: 661353 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 1.6136. Min Range: -1.6136

Max Act: 0.9833. Min Act: -0.0000

Data Index: 422375 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 1.6136. Min Range: -1.6136

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1734837 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 1.6136. Min Range: -1.6136

Max Act: 0.9540. Min Act: -0.0000

Data Index: 339296 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0072. Min Act: -0.0000

Data Index: 292969 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 1.6136. Min Range: -1.6136

Max Act: 0.7836. Min Act: -0.0000

Data Index: 718492 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 1.6136. Min Range: -1.6136

Max Act: 1.0072. Min Act: -0.0000

Data Index: 881003 (The Pile)

Max Activating Token Index: 531